近年來，類神經網路廣受眾人重視與投入研究，因為其具有適應學習能力、容錯能力、以及可以經由實例學習的方式建構系統，以建立網路輸入與輸出間對應關係，並不斷進行學習與修正，解決許多複雜問題。類神經網路的研究已經廣泛應用於各種領域，如工程分析與設計、機電設備診斷、數位影像處理分析、產品品質分析、商業金融管理等。
本研究結合類神經網路與二維離散小波轉換應用於偵測板架結構的裂縫損傷程度。在數值模擬上，首先以有限元素模擬含有缺陷的板架結構，並以二維離散小波分析板架結構的模態振型，並擷取其類神經網路的訓練樣本，藉此架構一套可以判別板架結構裂縫損傷程度的偵測系統。在實驗分析上，先以激振器給予板架結構ㄧ衝擊外力，然後以加速規量測板架結構的振動訊號，接著以小波包轉換從振動訊號中找出板架結構的模態振型，最後將實驗所得之模態振型，經由多尺度二維離散小波分析，並將對角方向之高頻訊號取均方根值來計算，以此來作為實驗之損傷指標，最後匯入模擬已建構的類神經網路中，偵測板架結構的損傷程度。

During recent decades, there has been an increase in the number of researchers who have devoted themselves to artificial neural networks. This method has many useful characteristics that appeal to such researchers, including adaptation learning capability, fault-tolerant capability, and the ability to use practice examples to build a neural networks system. The method can process complex information and establish the correspondence between input and output relationships by learning and revision. Therefore, the neural networks have been widely used in various fields, such as analysis and design of industrial engineering system, diagnosis of mechatronics engineering system, digital image processing and analysis, quality of products analysis, and commercial financial management.
In this study, two-dimensional discrete wavelet transforms and artificial neural network are utilized to identify single cracks or multi-cracks in stiffened plates. In numerical analysis, based on the dynamic properties of a stiffened plate before and after the damage has been dealt, the mode shapes for the stiffened plates are computed by FEM. The two-dimensional discrete wavelet transforms are applied to analyze the mode shapes of the stiffened plates, and then the obtained training samples of neural networks are used to establish the damage identification system for identifying the damage degree of a crack in stiffened plates. In the experiment analysis, several accelerometers are used to measure the vibration responses of the stiffened plate, and the first mode shapes of the stiffened plate are attained by using the wavelet packet analysis. The experimental damage indices are obtained by two-dimensional discrete wavelet transforms and artificial neural network. Finally, the results of the experiments are compared to the damage identification system used to detect the damage degree of the crack in the stiffened plates.

[1]Cawley, P., and Adams, R. D.,“The Location of Defects in Structures from Measurement of Natural Frequencies,”Journal of Strain Analysis, 14, 1979.
[2]Choubey, A. , D. K. Sehgal and N. Tandon ,“Finite element analysis of vessels to study changes in natural frequencies due to cracks,” International Journal of Pressure Vessels and Piping, Vol. 83, Issue 3, pp.181-187 , 2006.
[3]Chen, Wenyuan , Lei Zhao and Guotang Bi,“Application of neural network and wavelet analysis in monitoring multiple structural damage,”International Conference on Electronic Measurement and Instruments, pp. 4463-4467, 2007.
[4]Daubechies, I.,“Ten Lectures on Wavelets,”SIAM, Philadelphia, 1992.
[5]Deng, X., Wang, Q.,“Crack Detection Using Spatial Measurements and Wavelet,”　International Journal of Fracture, Vol. 91, 1998.
[6]Diao, Yan-Song, Hua-Jun Li and Yan Wang,“A two-step structural damage detection approach based on wavelet packet analysis and neural network,”Proceedings of the 2006 International Conference on Machine Learning and Cybernetics, pp.3128-3133, 2006.
[7]Kudva, J. N. , N. Munir and P. W. Tan,“Damage detection in smart structures using neural networks and finite-element analyses,” Smart Materials and Structures, Vol.1, NO.2, pp. 108-112, 1992.
[8]Liew, K. M., Wang, Q.,“Application of Wavelet Theory for Crack Identication in Structures,”Journal of Engineering Mechanics, Vol.124(2), pp.152-157, 1998.
[9]Loutridis, S., Douka, E., and Trochidis, A.,“Crack Identification in Beams Using Wavelet Analysis,”International Journal of Solids and Structures , Vol.40, pp.3557-3569, 2003.
[10]Mallat, S. G.,“A Theory for Multiresolution Signal Decomposition, The Wave Representation,”Comm. Pure Appl. Math, 41, pp.674-693, 1988.
[11]Messina, A., Jones, I. A., “Damage Detection and Localization Using Natural Frequency Change,”14th International Modal Analysis Conference, Orlando, pp.67-76, 1996.
[12]Meyer, Y. Ondettes et Functions Splines Lectures given at the University of Torino, Italy, 1986.
[13]Meyer, Y., Ondettes, Functions Splines et Analyses Graduees, Seminaire EDP, Ecole Polytechnique, Paris, France, 1986.
[14]Meyer, Y.,“Wavelets Algorithms and Application,”Siam, 1993.
[15]Morlet, J., Arens, G., Fourgeau, I., and Giard, D.,“Wave Propagation and Sampling Theory”Geophysics, 47, pp.203-236, 1982.
[16]Morlet, J.,“Sampling Theory and Wave Propagation”, NATO ASI Series, Issues in Acoustic Signal/Image Processing and Recognition , Vol. I, pp.233-261, 1983.
[17]Surace, C., and Ruotolo, R.,“Crack Detection of a Beam Using the Wavelet Transform,”Proceedings of the 12th International Modal Analysis Conference, Honolulu, pp.1141-1147, 1994.
[18]Wang, Q., Deng, X.,“Damage Detection with Spatial Wavelets,”International Journal of Solids and Structures, Vol.36, pp.3443-3468, 1999.
[19]Werner Soedel,“Vibrations of Shells and Plates,”Marcel Dekker, America, 1993.
[20]Yam, L. H. , Y.J. Yan and J.S. Jiang,“Vibration-based damage detection for composite structures using wavelet transform and neural network identification,”Composite Structures, Vol. 60, Issue 4, pp. 403-412, 2003.
[21]Yam, L. H. , Y. J. Yan , L. Cheng and J. S. Jiang,“Identification of complex crack damage for honeycomb sandwich plate using wavelet analysis and neural networks,”Smart Materials and Structures, Vol.12, NO.5, pp. 661-671, 2003.
[22]Yang, J. M., C. N. Hwang and B. L. Yang,“Crack Identification in Beams and Plates by Discrete Wavelet Transform Method,”Journal of Ship Mechanics,Vol.3,NO. 3,pp.464-472,2008.
[23]Zang, C. and M. Imregun,“Structural damage detection using artificial neural networks and measured FRF data reduced via principal component projection,”Journal of Sound and Vibration, Vol. 242, NO. 5, pp. 813-827, 2001.
[24]長思科技產品研發中心,“MATLAB6.5輔助小波分析與應 用,”電子工業出版社,北京,2003.
[25]周鵬程,“類神經網路入門-活用Matlab,”全華科技圖書股份有限公司,2002.
[26]周志豪,“應用類神經網路於主動振動控制之研究,”南台科技大學機械工程系研究所,碩士論文,中華民國九十五年六月.
[27]林子超,“類神經網路在結構損傷偵測分析的應用,”國立成功大學航空太空工程研究所,碩士論文,中華民國八十六年六月.
[28]胡昌華等,“基於MATLAB的系統分析與設計：小波分析,”西安電子科技大學出版社,中國大陸,1999.
[29]許有村,“小波理論在機械結構破壞點偵測上的應用,”國立台灣大學機械工程研究所, 碩士論文, 中華民國八十七年六月.
[30]陳精一,蔡國忠,“電腦輔助工程分析ANSYS使用指南,”全華科技股份有限公司, 台灣, 2000.
[31]張智傑,“小波訊號處理於結構破損偵測之應用,”國立成功大學機械工程學系,博士論文,中華民國九十三年六月.
[32]張哲銘,“結合類神經網路與二維離散小波轉換應用於多重裂縫平板破損偵測之研究,”國立成功大學系統暨船舶機電工程學系, 碩士論文, 中華民國九十九年七月.
[33]曾韋鳴,“利用類神經網路結合離散小波轉換進行樑與板之破損偵測,”國立成功大學系統暨船舶機電工程學系, 碩士論文, 中華民國九十九年六月.
[34]單維彰,“凌波初步,”全華科技, 台灣, 2000.
[35]楊澤民,廖翊宏, 嵇泓鈞,“小波理論應用於樑的破損偵測之究,” 中國造船暨輪機工程學刊,Vol.23,No.4,pp.189-197,2004.
[36]楊澤民,黃正能,柯志宏,曾韋鳴,“二維離散小波轉換應用於帶有加強材之平板破損偵測,”中國造船暨輪機工程學刊,Vol.28,No.1,pp.29-40,2009.
[37]楊澤民,楊正瑋, “小波轉換應用於板架結構的損傷偵測,” 中國造船暨輪機工程學刊,Vol.28,No.4,pp.221-235,2009.
[38]黎文明, “快速傅立葉轉換,”復漢出版社, 台灣, 1985.
[39]蔡展榮,“小波基礎理論與應用課程講義,”國立成功大學空間及測量工程學系研究所, 2002.
[40]蔡哲緯,“應用類神經網路於結構損傷定位之研究,”國立成功大學航空太空工程研究所,碩士論文,中華民國九十七年六月.
[41]劉晉奇,褚晴暉,“有限元素分析與ANSYS的工程應用,”滄海書局, 台灣, 2006.
[42]鐘啟聞,“應用類神經網路與自然頻率於結構物之損壞預測,”國立成功大學造船暨船舶機械工程研究所,碩士論文,中華民國九十一年六月.
[43]羅華強,“類神經網路-Matlab的應用,”高立圖書有限公司, 台灣,2008.